sbi

sbi copied to clipboard

Score-based density estimators for SBI

3

## What does this implement/fix? Explain your changes This PR implements score-based methods for SBI (and related methods like flow matching). The first goal is to have a running version...

jsvetter

feat: flow matching methods

2

## What does this implement/fix? Explain your changes Implements basic Flow Matchting Posterior Estimation as described by [Dax et al.](https://arxiv.org/abs/2305.17161) ## Does this close any currently open issues? Fixes #963...

turnmanh

Make code formatting easier and less painful

5

There seem to be different local versions of ruff for different contributors, and successive PRs from different contributors change the same files back and forth depending on local versions. Need...

gmoss13

prepare_for_sbi causes import error with the latest scipy

1

Hi, just a heads-up, if you have scipy version>=1.13.0, you will get an import error because of an issue with arviz. (https://discourse.pymc.io/t/importerror-cannot-import-name-gaussian-from-scipy-signal/14170) In other words, if you do: `from sbi.inference...

jiseonmin

As all neural networks in `sbi`, the `MixedDensityEstimator` should also be allowed to have an `embedding_net`. This is especially critical if we intent to use the `MixedDensityEstimator` also to estimate...

michaeldeistler

Currently, the `build_categoricalmassestimator` does [not take arguments for z-scoring](https://github.com/sbi-dev/sbi/blob/0f0ee6e9f6c35a6d030281427409bcfacc0e4764/sbi/neural_nets/categorial.py#L12-L16). Instead, since it is only actively used in MNLE, `build_mnle` takes care of z-scoring by passing a standarization net to the...

michaeldeistler

ENH add h npe

1

## What does this implement/fix? Explain your changes Implement hNPE, from this paper: https://arxiv.org/abs/2102.06477 This PR adds: - a `hierachical_simulator` decorator to wrap simulator and generate simulation with extra observations....

tomMoral

The [README of the tutorials](https://github.com/sbi-dev/sbi/blob/main/tutorials/README.md) separates tutorials between users and contributors in a too strong way. In fact, all tutorials are for users, not for contributors. In addition, the README...

michaeldeistler

In #1066, I did not update the `log_prob_iid` method. Instead, MNLE currently uses the standard `log_prob()` to sample [here](https://github.com/sbi-dev/sbi/blob/0f0ee6e9f6c35a6d030281427409bcfacc0e4764/sbi/inference/potentials/likelihood_based_potential.py#L217-L221). For improved sampling speed we should revert to using `log_prob_iid()`

michaeldeistler

base_dist methods for nflows and zuko

1

Same as issue #1085 fixed in PR #1086 for the inverse-transform method.

JuliaLinhart